# Physical Intelligence: VLA models show human-to-robot transfer as robot data scale grows

- Source: Physical Intelligence
- Published: 2025-12-15T16:00:00.000Z
- RoboHot: https://robohot.news/en/items/z0v3yrjadbp2zsx87shklmhes
- Original: https://www.pi.website/research/human_to_robot

## Summary

Physical Intelligence research found that in generalization scenarios where only human demonstrations appear, fine-tuning π0.5 with human first-person videos mixed into robot data alone improved policy performance by about 2x, without using any explicit transfer learning mechanism.

## Why it matters

Experiments show that merely mixing human videos into fine-tuning improves the policy by about 2x on scenarios with purely human demonstrations, and this capability emerges as pretraining robot data scale grows.